Multiresolution Fourier-Wavelet Descriptor for Fingerprint Recognition

This paper present a multiresolution descriptors for fingerprint recognition .The first step in our method is compute the Discrete Fourier Transform (DFT) for the given fingerprint image then we transform it to polar coordinate (r,thetas ) using the centre of mass of the pattern as origin, then apply the Fourier transform along the axis of polar angle thetas and the wavelet transform along the axis of radius r. The features thus obtained are invariant to translation, rotation, and scaling. The performance is evaluated by the k-nearest neighbour (k-NN) classifier.